Model comparison
Impish_QWEN_14B-1M vs Qwen3.8-27B
At Q4_K_M, Impish_QWEN_14B-1M is the smaller download — 8,988,108,032 bytes against 16,810,714,336. At long context the gap widens: Qwen3.8-27B's KV cache at 32K is 3.0× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| Impish_QWEN_14B-1M | Qwen3.8-27B | |
|---|---|---|
| Parameters | 14.8B | 27.8B |
| Architecture | qwen2 | qwen35 |
| Layers | 48 | 64 |
| Native context | 1,010,000 | 262,144 |
| Mixture of experts | no | no |
| Quantizations published | 33 | 22 |
| Smallest quantization | 3.36 GiB | 8.39 GiB |
| Q4_K_M | 8.37 GiB | 15.66 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Impish_QWEN_14B-1M | Qwen3.8-27B | Ratio |
|---|---|---|---|
| 4,096 | 0.75 GiB | 0.25 GiB | 3.00× |
| 8,192 | 1.50 GiB | 0.50 GiB | 3.00× |
| 16,384 | 3.00 GiB | 1.00 GiB | 3.00× |
| 32,768 | 6.00 GiB | 2.00 GiB | 3.00× |
| 65,536 | 12.00 GiB | 4.00 GiB | 3.00× |
| 131,072 | 24.00 GiB | 8.00 GiB | 3.00× |